Part-DB-server/src/Services/InfoProviderSystem/Providers/BuerklinProvider.php

<?php
/*
 * This file is part of Part-DB (https://github.com/Part-DB/Part-DB-symfony).
 *
 *  Copyright (C) 2019 - 2023 Jan Böhmer (https://github.com/jbtronics)
 *  Copyright (C) 2025 Marc Kreidler (https://github.com/mkne)
 *
 *  This program is free software: you can redistribute it and/or modify
 *  it under the terms of the GNU Affero General Public License as published
 *  by the Free Software Foundation, either version 3 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU Affero General Public License for more details.
 *
 *  You should have received a copy of the GNU Affero General Public License
 *  along with this program.  If not, see <https://www.gnu.org/licenses/>.
 */

declare(strict_types=1);


namespace App\Services\InfoProviderSystem\Providers;

use App\Services\InfoProviderSystem\DTOs\FileDTO;
use App\Services\InfoProviderSystem\DTOs\ParameterDTO;
use App\Services\InfoProviderSystem\DTOs\PartDetailDTO;
use App\Services\InfoProviderSystem\DTOs\PriceDTO;
use App\Services\InfoProviderSystem\DTOs\PurchaseInfoDTO;
use Symfony\Component\HttpFoundation\Cookie;
use Symfony\Component\HttpClient\HttpOptions;
use Symfony\Contracts\HttpClient\HttpClientInterface;

class BuerklinProvider implements InfoProviderInterface
{

    private const ENDPOINT_URL = 'https://buerklin.com/buerklinws/v2/buerklin/';

    public const DISTRIBUTOR_NAME = 'Buerklin';
    private const OAUTH_APP_NAME = 'ip_buerklin_oauth';

    public function __construct(private readonly HttpClientInterface $httpClient,
        private readonly OAuthTokenManager $authTokenManager, private readonly CacheItemPoolInterface $partInfoCache,
        private readonly string $clientId, private readonly string $secret,
        private readonly int $username, private readonly bool $password,
        private readonly string $currency, private readonly string $language)
    {

    }

    /**
     * Gets the latest OAuth token for the Buerklin API, or creates a new one if none is available
     * @return string
     */
    private function getToken(): string
    {
        //Check if we already have a token saved for this app, otherwise we have to retrieve one via OAuth
        if (!$this->authTokenManager->hasToken(self::OAUTH_APP_NAME)) {
            $this->authTokenManager->retrieveClientCredentialsToken(self::OAUTH_APP_NAME);
        }

        $tmp = $this->authTokenManager->getAlwaysValidTokenString(self::OAUTH_APP_NAME);
        if ($tmp === null) {
            throw new \RuntimeException('Could not retrieve OAuth token for Buerklin');
        }

        return $tmp;
    }

    public function getProviderInfo(): array
    {
        return [
            'name' => 'Buerklin',
            'description' => 'This provider uses the Buerklin API to search for parts.',
            'url' => 'https://www.buerklin.com/',
            'disabled_help' => 'Set the environment variables PROVIDER_BUERKLIN_CLIENT_ID, PROVIDER_BUERKLIN_SECRET, PROVIDER_BUERKLIN_USERNAME and PROVIDER_BUERKLIN_PASSWORD.'
        ];
    }

    public function getProviderKey(): string
    {
        return 'buerklin';
    }

    // This provider is always active
    public function isActive(): bool
    {
        //The client ID has to be set and a token has to be available (user clicked connect)
        return $this->clientId !== '' && $this->secret !== '' && $this->username !== '' && $this->password !== '';
    }

    /**
     * @param  string  $id
     * @return PartDetailDTO
     */
    private function queryDetail(string $id): PartDetailDTO
    {
        $response = $this->buerklinClient->request('GET', self::ENDPOINT_URL . "/products", [
            'headers' => [
                'Cookie' => new Cookie('currencyCode', $this->currency)
            ],
            'query' => [
                'sku' => $id,
            ],
        ]);

        $arr = $response->toArray();
        $product = $arr['result'] ?? null;

        if ($product === null) {
            throw new \RuntimeException('Could not find product code: ' . $id);
        }

        return $this->getPartDetail($product);
    }

    /**
     * @param  string  $url
     * @return String
     */
    private function getRealDatasheetUrl(?string $url): string
    {
        if ($url !== null && trim($url) !== '' && preg_match("/^https:\/\/(datasheet\.buerklin\.com|www\.buerklin\.com\/datasheet)\/.*(C\d+)\.pdf$/", $url, $matches) > 0) {
          if (preg_match("/^https:\/\/datasheet\.buerklin\.com\/buerklin\/(.*\.pdf)$/", $url, $rewriteMatches) > 0) {
            $url = 'https://www.buerklin.com/datasheet/buerklin_datasheet_' . $rewriteMatches[1];
          }
          $response = $this->buerklinClient->request('GET', $url, [
              'headers' => [
                  'Referer' => 'https://www.buerklin.com/de/p/' . $matches[2] . '/'
              ],
          ]);
          if (preg_match('/(previewPdfUrl): ?("[^"]+wmsc\.buerklin\.com[^"]+\.pdf")/', $response->getContent(), $matches) > 0) {
            //HACKY: The URL string contains escaped characters like \u002F, etc. To decode it, the JSON decoding is reused
            //See https://github.com/Part-DB/Part-DB-server/pull/582#issuecomment-2033125934
            $jsonObj = json_decode('{"' . $matches[1] . '": ' . $matches[2] . '}');
            $url = $jsonObj->previewPdfUrl;
          }
        }
        return $url;
    }

    /**
     * @param  string  $term
     * @return PartDetailDTO[]
     */
    private function queryByTerm(string $term): array
    {
        $response = $this->buerklinClient->request('GET', self::ENDPOINT_URL . "products/search/?curr=$this->currency&language=en&pageSize=50&currentPage=0&query=Laser&sort=relevance", [
            'headers' => [
                'Cookie' => new Cookie('currencyCode', $this->currency)
            ],
            'query' => [
                'keyword' => $term,
            ],
        ]);

        $arr = $response->toArray();

        // Get products list
        $products = $arr['result']['productSearchResultVO']['productList'] ?? [];
        // Get product tip
        $tipProductCode = $arr['result']['tipProductDetailUrlVO']['productCode'] ?? null;

        $result = [];

        // Buerklin does not display Buerklin codes in the search, instead taking you directly to the
        // detailed product listing. It does so utilizing a product tip field.
        // If product tip exists and there are no products in the product list try a detail query
        if (count($products) === 0 && $tipProductCode !== null) {
            $result[] = $this->queryDetail($tipProductCode);
        }

        foreach ($products as $product) {
            $result[] = $this->getPartDetail($product);
        }

        return $result;
    }

    /**
     * Sanitizes a field by removing any HTML tags and other unwanted characters
     * @param  string|null  $field
     * @return string|null
     */
    private function sanitizeField(?string $field): ?string
    {
        if ($field === null) {
            return null;
        }

        return strip_tags($field);
    }


    /**
     * Takes a deserialized json object of the product and returns a PartDetailDTO
     * @param  array  $product
     * @return PartDetailDTO
     */
    private function getPartDetail(array $product): PartDetailDTO
    {
        // Get product images in advance
        $product_images = $this->getProductImages($product['productImages'] ?? null);
        $product['productImageUrl'] ??= null;

        // If the product does not have a product image but otherwise has attached images, use the first one.
        if (count($product_images) > 0) {
            $product['productImageUrl'] ??= $product_images[0]->url;
        }

        // Buerklin puts HTML in footprints and descriptions sometimes randomly
        $footprint = $product["encapStandard"] ?? null;
        //If the footprint just consists of a dash, we'll assume it's empty
        if ($footprint === '-') {
            $footprint = null;
        }

        //Build category by concatenating the catalogName and parentCatalogName
        $category = $product['parentCatalogName'] ?? null;
        if (isset($product['catalogName'])) {
            $category = ($category ?? '') . ' -> ' . $product['catalogName'];

            // Replace the / with a -> for better readability
            $category = str_replace('/', ' -> ', $category);
        }

        return new PartDetailDTO(
            provider_key: $this->getProviderKey(),
            provider_id: $product['productCode'],
            name: $product['productModel'],
            description: $this->sanitizeField($product['productIntroEn']),
            category: $this->sanitizeField($category ?? null),
            manufacturer: $this->sanitizeField($product['brandNameEn'] ?? null),
            mpn: $this->sanitizeField($product['productModel'] ?? null),
            preview_image_url: $product['productImageUrl'],
            manufacturing_status: null,
            provider_url: $this->getProductShortURL($product['productCode']),
            footprint: $this->sanitizeField($footprint),
            datasheets: $this->getProductDatasheets($product['pdfUrl'] ?? null),
            images: $product_images,
            parameters: $this->attributesToParameters($product['paramVOList'] ?? []),
            vendor_infos: $this->pricesToVendorInfo($product['productCode'], $this->getProductShortURL($product['productCode']), $product['productPriceList'] ?? []),
            mass: $product['weight'] ?? null,
        );
    }

    /**
     * Converts the price array to a VendorInfoDTO array to be used in the PartDetailDTO
     * @param  string $sku
     * @param  string $url
     * @param  array  $prices
     * @return array
     */
    private function pricesToVendorInfo(string $sku, string $url, array $prices): array
    {
        $price_dtos = [];

        foreach ($prices as $price) {
            $price_dtos[] = new PriceDTO(
                minimum_discount_amount: $price['ladder'],
                price: $price['productPrice'],
                currency_iso_code: $this->getUsedCurrency($price['currencySymbol']),
                includes_tax: false,
            );
        }

        return [
            new PurchaseInfoDTO(
                distributor_name: self::DISTRIBUTOR_NAME,
                order_number: $sku,
                prices: $price_dtos,
                product_url: $url,
            )
        ];
    }

    /**
     * Converts Buerklin currency symbol to an ISO code.
     * @param  string  $currency
     * @return string
     */
    private function getUsedCurrency(string $currency): string
    {
        //Decide based on the currency symbol
        return match ($currency) {
            'US$', '$' => 'USD',
            '€' => 'EUR',
            'A$' => 'AUD',
            'C$' => 'CAD',
            '£' => 'GBP',
            'HK$' => 'HKD',
            'JP¥' => 'JPY',
            'RM' => 'MYR',
            'S$' => 'SGD',
            '₽' => 'RUB',
            'kr' => 'SEK',
            'kr.' => 'DKK',
            '₹' => 'INR',
            //Fallback to the configured currency
            default => $this->currency,
        };
    }

    /**
     * Returns a valid Buerklin product short URL from product code
     * @param  string  $product_code
     * @return string
     */
    private function getProductShortURL(string $product_code): string
    {
        return 'https://www.buerklin.com/de/p/' . $product_code .'/';
    }

    /**
     * Returns a product datasheet FileDTO array from a single pdf url
     * @param  string  $url
     * @return FileDTO[]
     */
    private function getProductDatasheets(?string $url): array
    {
        if ($url === null) {
            return [];
        }

        $realUrl = $this->getRealDatasheetUrl($url);

        return [new FileDTO($realUrl, null)];
    }

    /**
     * Returns a FileDTO array with a list of product images
     * @param  array|null  $images
     * @return FileDTO[]
     */
    private function getProductImages(?array $images): array
    {
        return array_map(static fn($image) => new FileDTO($image), $images ?? []);
    }

    /**
     * @param  array|null  $attributes
     * @return ParameterDTO[]
     */
    private function attributesToParameters(?array $attributes): array
    {
        $result = [];

        foreach ($attributes as $attribute) {

            //Skip this attribute if it's empty
            if (in_array(trim((string) $attribute['paramValueEn']), ['', '-'], true)) {
              continue;
            }

            $result[] = ParameterDTO::parseValueIncludingUnit(name: $attribute['paramNameEn'], value: $attribute['paramValueEn'], group: null);
        }

        return $result;
    }

    public function searchByKeyword(string $keyword): array
    {
        return $this->queryByTerm($keyword);
    }

    public function getDetails(string $id): PartDetailDTO
    {
        $tmp = $this->queryByTerm($id);
        if (count($tmp) === 0) {
            throw new \RuntimeException('No part found with ID ' . $id);
        }

        if (count($tmp) > 1) {
            throw new \RuntimeException('Multiple parts found with ID ' . $id);
        }

        return $tmp[0];
    }

    public function getCapabilities(): array
    {
        return [
            ProviderCapabilities::BASIC,
            ProviderCapabilities::PICTURE,
            ProviderCapabilities::DATASHEET,
            ProviderCapabilities::PRICE,
            ProviderCapabilities::FOOTPRINT,
        ];
    }
}